SpikeBASE: Spiking Neural Learning Algorithm With Backward Adaptation of Synaptic Efflux

• Published in: IEEE transactions on computers Vol. 71; no. 11; pp. 2707 - 2716
• Main Authors: Stauffer, Jake, Zhang, Qingxue
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.11.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptation; Algorithms; artificial intelligence; Back propagation; Back propagation networks; Backpropagation; Big Data; Brain modeling; Cognitive tasks; Deep learning; Effectiveness; Efflux; Heuristic algorithms; Machine learning; neural models; Neural networks; Neuromorphic computing; Neurons; Spatiotemporal phenomena; Spiking; Training
• ISSN: 0018-9340; 1557-9956
• DOI: 10.1109/TC.2022.3197089

Brain-inspired Spiking Neural Network (SNN) is opening new possibilities towards human-level intelligence, by leveraging its nature of spatiotemporal information encoding and processing that bring both learning effectiveness and energy efficiency. Although substantial advances in SNN studies have been made, highly effective SNN learning algorithms are still urged, driven by the challenges of coordinating spiking spatiotemporal dynamics. We therefore propose a novel algorithm, SpikeBASE, denoting Spiking learning with Backward Adaption of Synaptic Efflux, to globally, supervisedly, and comprehensively coordinate the synaptic dynamics including both synaptic strength and responses. SpikeBASE can learn synaptic strength by backpropagating the error through the predefined synaptic responses. More importantly, SpikeBASE enables synaptic response adaptation through backpropagation, to mimic the complex dynamics of neural transmissions. Further, SpikeBASE enables multi-scale temporal memory formation by supporting multi-synaptic response adaptation. We have evaluated the algorithm on a challenging scarce data learning task and shown highly promising performance. The proposed SpikeBASE algorithm, through comprehensively coordinating the learning of synaptic strength, synaptic responses, and multi-scale temporal memory formation, has demonstrated its effectiveness on end-to-end SNN training. This study is expected to greatly advance the learning effectiveness of SNN and thus broadly benefit smart and efficient big data applications.